Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }`}
    -0.07
    .characters
    -0.06
    围
    -0.06
     Під
    -0.06
     impunity
    -0.06
    ’aut
    -0.06
    (count
    -0.06
     getOrder
    -0.06
     randint
    -0.06
     직
    -0.06
    POSITIVE LOGITS
    ottenham
    0.06
    ISING
    0.06
    acerb
    0.06
     budouc
    0.06
    럼
    0.06
    ackBar
    0.06
     creepy
    0.06
    ellite
    0.06
     starší
    0.06
    tabla
    0.06
    Act Density 0.022%

    No Known Activations